Skip to content

Actions: ModelTC/lightllm

Actions

Pre-commit checks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
363 workflow runs
363 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

complete all_reduce and test
Pre-commit checks #345: Pull request #619 synchronize by WANDY666
November 27, 2024 05:19 27s pynccl2
November 27, 2024 05:19 27s
complete all_reduce and test
Pre-commit checks #344: Pull request #619 opened by WANDY666
November 27, 2024 03:01 30s pynccl2
November 27, 2024 03:01 30s
upgrade deepseek kv copy & fix test/model_infer.py
Pre-commit checks #343: Pull request #617 synchronize by shihaobai
November 26, 2024 11:50 29s mla_att
November 26, 2024 11:50 29s
upgrade deepseek kv copy & fix test/model_infer.py
Pre-commit checks #342: Pull request #617 opened by shihaobai
November 26, 2024 11:48 31s mla_att
November 26, 2024 11:48 31s
optimze decode mla att
Pre-commit checks #341: Pull request #616 synchronize by shihaobai
November 26, 2024 06:36 30s mla_att
November 26, 2024 06:36 30s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #340: Pull request #615 synchronize by WANDY666
November 26, 2024 06:34 26s pynccl2
November 26, 2024 06:34 26s
optimze decode mla att
Pre-commit checks #339: Pull request #616 synchronize by shihaobai
November 26, 2024 06:14 31s mla_att
November 26, 2024 06:14 31s
optimze decode mla att
Pre-commit checks #338: Pull request #616 synchronize by shihaobai
November 26, 2024 06:10 39s mla_att
November 26, 2024 06:10 39s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #337: Pull request #615 synchronize by WANDY666
November 26, 2024 03:06 29s pynccl2
November 26, 2024 03:06 29s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #336: Pull request #615 synchronize by WANDY666
November 26, 2024 02:47 26s pynccl2
November 26, 2024 02:47 26s
optimze decode mla att
Pre-commit checks #335: Pull request #616 synchronize by shihaobai
November 25, 2024 10:58 31s mla_att
November 25, 2024 10:58 31s
optimze decode mla att
Pre-commit checks #334: Pull request #616 opened by shihaobai
November 25, 2024 10:49 29s mla_att
November 25, 2024 10:49 29s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #333: Pull request #615 synchronize by WANDY666
November 25, 2024 10:16 38s pynccl2
November 25, 2024 10:16 38s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #332: Pull request #615 opened by WANDY666
November 25, 2024 10:08 28s pynccl2
November 25, 2024 10:08 28s
Deepseek2 Support PD mode
Pre-commit checks #331: Pull request #614 opened by hiworldwzj
November 25, 2024 05:30 37s wzj_pd
November 25, 2024 05:30 37s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #330: Pull request #613 synchronize by WANDY666
November 22, 2024 10:26 29s pynccl
November 22, 2024 10:26 29s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #329: Pull request #613 synchronize by shihaobai
November 22, 2024 10:20 30s pynccl
November 22, 2024 10:20 30s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #328: Pull request #613 synchronize by WANDY666
November 22, 2024 09:26 30s pynccl
November 22, 2024 09:26 30s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #327: Pull request #613 synchronize by WANDY666
November 22, 2024 09:23 30s pynccl
November 22, 2024 09:23 30s
add vllm pynccl for cuda graph compatibility
Pre-commit checks #326: Pull request #613 opened by WANDY666
November 22, 2024 09:11 33s pynccl
November 22, 2024 09:11 33s
refact quantization, support torchao quant and vllm w8a8(int/fp), support mix quantization.
Pre-commit checks #325: Pull request #596 synchronize by hiworldwzj
November 22, 2024 06:45 28s quantization
November 22, 2024 06:45 28s
refact quantization, support torchao quant and vllm w8a8(int/fp), support mix quantization.
Pre-commit checks #324: Pull request #596 synchronize by hiworldwzj
November 22, 2024 06:43 32s quantization
November 22, 2024 06:43 32s
refact quantization, support torchao quant and vllm w8a8(int/fp), support mix quantization.
Pre-commit checks #323: Pull request #596 synchronize by shihaobai
November 22, 2024 06:03 33s quantization
November 22, 2024 06:03 33s
refact quantization, support torchao quant and vllm w8a8(int/fp), support mix quantization.
Pre-commit checks #322: Pull request #596 synchronize by shihaobai
November 22, 2024 04:36 26s quantization
November 22, 2024 04:36 26s
refact quantization, support torchao quant and vllm w8a8(int/fp), support mix quantization.
Pre-commit checks #321: Pull request #596 synchronize by shihaobai
November 22, 2024 04:33 32s quantization
November 22, 2024 04:33 32s